Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Ken-Technology/cold-email-skills --skill lead-magnetgit clone --depth 1 https://github.com/Ken-Technology/cold-email-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ken-technology/cold-email-skills/lead-magnet)<a href="https://agentmods.dev/skills/ken-technology/cold-email-skills/lead-magnet"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/lead-magnet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ken-technology/cold-email-skills/lead-magnet"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/lead-magnet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02935 |
| Opus 5.5 | $0.00023 | $0.01174 |
| Sonnet 5.5 | $0.00012 | $0.00587 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade A, and why
lead-magnet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Magnet Skill
Ideate and design lead magnets that attract ideal customers and make them more likely to buy the client's core offering. Supports both click-based campaigns (landing pages, downloads) and reply-based campaigns (free trials, guarantees, done-for-you).
This is the optional offer stage of the campaign workflow (create-campaign, also installed as cold-email-campaign): run it before the plan when the client has no strong offer, or when the user asks for offer ideas. This skill designs the lead magnet; the client builds it on their own site or in their own tools.
Required inputs
- The campaign workspace (
./cold-email/{slug}/, passed by the orchestrator): readresearch.mdthere and writelead-magnets.mdthere. Without one, work from what the user gives you and return the output in the chat.
The rule: only real lead magnets reach copy
A concept from this stage is a recommendation until the client has built it and confirmed it is live. campaign-planning, campaign-strategy and email-copywriting reference or link a lead magnet only when it really exists. Never invent a guarantee, a price, a trial length, a result or a statistic: every one comes from the client's research or the client.
Core Philosophy
"Give Away The Secrets, Sell The Implementation"
The marketplace judges everything you offer - free or not. You can never provide too much value, but you can provide too little. The lead magnet should provide so much value that people feel obligated to pay. The goal is to provide more value than the cost of the core offer before they've bought it.
Two Campaign Types
Every lead magnet must be designed for one of these funnel types:
Click-Based (Landing Page Funnel)
- Flow: Cold email -> Click link -> Landing page -> Download/signup -> Nurture sequence
- Best for: SaaS products, digital tools, content-driven offers
- Lead magnets: Calculators, guides, scorecards, free tools, AI apps, templates
- Email goal: Clicks
- End goal: Sign-ups, downloads, free trial activations
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago Changed · -2 lines · -57 tokens per session 8829b0974699
- 2mo ago First seen · 254 lines · 115 tokens per session scan A 889f2cc5898b
lead-magnet is a skill published in the GitHub repository Ken-Technology/cold-email-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 2,935 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
lead-magnet compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lead-magnetKen-Technology/cold-email-skills | Skill | 4 | 6d ago | MIT | A | 58 | Claude Code, Codex |
| cold-emailFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 177 | Claude Code, Codex |
| list-buildingFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 190 | Claude Code, Codex |
| claygentFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 131 | Claude Code |
| conditional-logicFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 128 | Claude Code |
| people-enrichmentFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 110 | Claude Code |
| scoringFrontal-so/outbound-skills | Skill | 9 | 1mo ago | MIT | A | 113 | Claude Code |